Related papers: Cottontail: Large Language Model-Driven Concolic E…
Concolic execution is a powerful program analysis technique for exploring execution paths in a systematic manner. Compare to random-mutation-based fuzzing, concolic execution is especially good at exploring paths that are guarded by complex…
Automatically generating formal specifications including loop invariants, preconditions, and postconditions for legacy code is critical for program understanding, reuse and verification. However, the inherent complexity of control and data…
Ensuring both syntactic and semantic correctness in Large Language Model (LLM) outputs remains a significant challenge, despite being critical for real-world deployment. In this paper, we introduce $\texttt{SEM-CTRL}$, a unified approach…
The rapid advancement of Large Language Models (LLMs) has brought about remarkable generative capabilities but also raised concerns about their potential misuse. While strategies like supervised fine-tuning and reinforcement learning from…
Recently, pre-trained large language models (LLMs) have shown impressive abilities in generating codes from natural language descriptions, repairing buggy codes, translating codes between languages, and retrieving relevant code segments.…
Branch coverage of source code is a very widely used test criterion. Moreover, branch coverage is a similar problem to line coverage, MC/DC and the coverage of assertion violations, certain runtime errors and various other types of test…
The capabilities of Large Language Models (LLMs) have significantly evolved, extending from natural language processing to complex tasks like code understanding and generation. We expand the scope of LLMs' capabilities to a broader context,…
Training large language models (LLMs) with chain-of-thought (CoT) supervision has proven effective for enhancing their reasoning abilities. However, obtaining reliable and accurate reasoning supervision remains a significant challenge. We…
Concolic testing combines program execution and symbolic analysis to explore the execution paths of a software program. This paper presents the first concolic testing approach for Deep Neural Networks (DNNs). More specifically, we formalise…
Large language models (LLMs) have shown impressive in-context learning (ICL) ability in code generation. LLMs take a prompt consisting of requirement-code examples and a new requirement as input, and output new programs. Existing studies…
Large Language Models (LLMs) have shown strong performance in automated source-to-target code translation through pretraining on extensive code corpora. However, mainstream LLM-based code translation methods suffer from two critical…
Executing computer programs described in natural language has long been a pursuit of computer science. With the advent of enhanced natural language understanding capabilities exhibited by large language models (LLMs), the path toward this…
Many reasoning, planning, and problem-solving tasks share an intrinsic algorithmic nature: correctly simulating each step is a sufficient condition to solve them correctly. This work studies to what extent Large Language Models (LLMs) can…
Concolic testing is a promising method for generating test suites for large programs. However, it suffers from the path-explosion problem and often fails to find tests that cover difficult-to-reach parts of programs. In contrast, model…
Large Language Models (LLMs) have shown remarkable capabilities in code generation tasks, yet they face significant limitations in handling complex, long-context programming challenges and demonstrating complex compositional reasoning…
Code coverage is a widely used metric for quantifying the extent to which program elements, such as statements or branches, are executed during testing. Calculating code coverage is resource-intensive, requiring code building and execution…
As machine learning gains prominence in various sectors of society for automated decision-making, concerns have risen regarding potential vulnerabilities in machine learning (ML) frameworks. Nevertheless, testing these frameworks is a…
To effectively use large language models (LLMs) for real-world queries, it is imperative that they generalize to the long-tail distribution, i.e. rare examples where models exhibit low confidence. In this work, we take the first step…
Large Language Models (LLMs), such as GPT-4, StarCoder, and CodeLlama, are transforming the way developers approach programming by automatically generating code based on given natural language descriptions. Despite advancements, generating…
Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it…